{ "by_category": { "add-1d": { "correct": 70, "n": 71, "acc": 0.9859 }, "add-2d-carry": { "correct": 463, "n": 500, "acc": 0.926 }, "comparison": { "correct": 363, "n": 500, "acc": 0.726 }, "missing-addend": { "correct": 337, "n": 500, "acc": 0.674 }, "missing-factor": { "correct": 92, "n": 500, "acc": 0.184 }, "mul-1d": { "correct": 45, "n": 45, "acc": 1.0 }, "mul-2dx1d": { "correct": 398, "n": 500, "acc": 0.796 }, "sub-borrow": { "correct": 493, "n": 500, "acc": 0.986 }, "two-step": { "correct": 163, "n": 500, "acc": 0.326 }, "which-bigger": { "correct": 277, "n": 300, "acc": 0.9233 } }, "runtime": "llama.cpp Q8_0 aggregate summary" }